Personalization of automatic speech recognition (ASR) models is a widely studied topic because of its many practical applications. Most recently, attention-based contextual biasing techniques are used to improve the recognition of rare words and/or domain specific entities. However, due to performance constraints, the biasing is often limited to a few thousand entities, restricting real-world usability. To address this, we first propose a “Retrieve and Copy” mechanism to improve latency while retaining the accuracy even when scaled to a large catalog. We also propose a training strategy to overcome the degradation in recall at such scale due to an increased number of confusing entities. Overall, our approach achieves up to 6% more Word Error Rate reduction (WERR) and 3.6% absolute improvement in F1 when compared to a strong baseline. Our method also allows for large catalog sizes of up to 20K without significantly affecting WER and F1-scores, while achieving at least 20% inference speedup per acoustic frame.

In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA). While self-training generates synthetic training data where natural inputs are aligned with noisy outputs, back-training results in natural outputs aligned with noisy inputs. This significantly reduces the gap between target domain and synthetic data distribution, and reduces model overfitting to source domain. We run UDA experiments on question generation and passage retrieval from the Natural Questions domain to machine learning and biomedical domains. We find that back-training vastly outperforms self-training by a mean improvement of 7.8 BLEU-4 points on generation, and 17.6% top-20 retrieval accuracy across both domains. We further propose consistency filters to remove low-quality synthetic data before training. We also release a new domain-adaptation dataset - MLQuestions containing 35K unaligned questions, 50K unaligned passages, and 3K aligned question-passage pairs.

Social media based micro-blogging sites like Twitter have become a common source of real-time information (impacting organizations and their strategies, and are used for expressing emotions and opinions. Automated analysis of such content therefore rises in importance. To this end, we explore the viability of using deep neural networks on the specific task of emotion intensity prediction in tweets. We propose a neural architecture combining convolutional and fully connected layers in a non-sequential manner - done for the first time in context of natural language based tasks. Combined with lexicon-based features along with transfer learning, our model achieves state-of-the-art performance, outperforming the previous system by 0.044 or 4.4% Pearson correlation on the WASSA’17 EmoInt shared task dataset. We investigate the performance of deep multi-task learning models trained for all emotions at once in a unified architecture and get encouraging results. Experiments performed on evaluating correlation between emotion pairs offer interesting insights into the relationship between them.

This paper describes our participation in SemEval 2018 Task 3 on Irony Detection in Tweets. We combine linguistic features with pre-trained activations of a neural network. The CNN is trained on the emoji prediction task. We combine the two feature sets and feed them into an XGBoost Classifier for classification. Subtask-A involves classification of tweets into ironic and non-ironic instances whereas Subtask-B involves classification of the tweet into - non-ironic, verbal irony, situational irony or other verbal irony. It is observed that combining features from these two different feature spaces improves our system results. We leverage the SMOTE algorithm to handle the problem of class imbalance in Subtask-B. Our final model achieves an F1-score of 0.65 and 0.47 on Subtask-A and Subtask-B respectively. Our system ranks 4th on both tasks respectively, outperforming the baseline by 6% on Subtask-A and 14% on Subtask-B.

The paper describes the best performing system for EmoInt - a shared task to predict the intensity of emotions in tweets. Intensity is a real valued score, between 0 and 1. The emotions are classified as - anger, fear, joy and sadness. We apply three different deep neural network based models, which approach the problem from essentially different directions. Our final performance quantified by an average pearson correlation score of 74.7 and an average spearman correlation score of 73.5 is obtained using an ensemble of the three models. We outperform the baseline model of the shared task by 9.9% and 9.4% pearson and spearman correlation scores respectively.